{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T20:01:17Z","timestamp":1792785677182,"version":"4.5.0"},"reference-count":40,"publisher":"IOP Publishing","issue":"9","license":[{"start":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T00:00:00Z","timestamp":1790640000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T00:00:00Z","timestamp":1790640000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"funder":[{"name":"European Union NextGenerationEU","id":[{"id":"https:\/\/ror.org\/019w4f821","id-type":"ROR","asserted-by":"crossref"}]}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Physiol. Meas."],"published-print":{"date-parts":[[2026,9,30]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    <jats:italic>Objective<\/jats:italic>\n                    . To develop an artifact-management method suitable for low-density, dry-electrode electroencephalogram (EEG) recorded from a wearable eyewear platform, enabling artifact detection, classification, and correction while avoiding unnecessary processing of clean neural activity.\n                    <jats:italic>Approach<\/jats:italic>\n                    . A gated two-stage pipeline is proposed in which a lightweight gate classifier first identifies artifact-contaminated EEG windows and selectively triggers further processing only when needed. The complete pipeline combines: (i) a time-domain feature-based detector, (ii) a convolutional\u2013recurrent network for three-class artifact discrimination (eye blinks, horizontal eye movements, facial movements), and (iii) a U-Net-based denoising autoencoder.\n                    <jats:italic>Main results<\/jats:italic>\n                    . Evaluated on the eyewear EEG dataset (29 subjects) using a leave-one-subject-out scheme, the gate classifier achieved a balanced accuracy of 0.89. The artifact classifier reached a balanced accuracy of 0.84 with a median macro-F1 of 0.83. The denoiser achieved a median normalized RMSE lower than 0.20 and a spectral cosine similarity above 0.84. In the end-to-end evaluation, the pipeline achieved a median normalized RMSE of 0.19 and a spectral cosine similarity of 0.89. Evaluation on an independent external benchmark showed that the proposed pipeline maintained a slightly lower gate detection performance (balanced accuracy 0.82) and achieved higher two-class classification performance. The denoising performance was comparable to that obtained on the dataset collected for this study, with absolute median differences not exceeding 0.04 for both normalized RMSE and spectral cosine similarity.\n                    <jats:italic>Significance<\/jats:italic>\n                    . These results support the effectiveness of the proposed approach for artifact management in wearable eyewear EEG, while maintaining a design compatible with resource-constrained wearable implementations.\n                  <\/jats:p>","DOI":"10.1088\/1361-6579\/ae99ab","type":"journal-article","created":{"date-parts":[[2026,8,13]],"date-time":"2026-08-13T22:53:17Z","timestamp":1786661597000},"page":"095010","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["A gated artifact management pipeline for low-density eyewear EEG"],"prefix":"10.1088","volume":"47","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-2379-1465","authenticated-orcid":true,"given":"Andrea","family":"Costanzo Palmisciano","sequence":"first","affiliation":[{"name":"Information and Bioengineering"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5582-4654","authenticated-orcid":true,"given":"Andrea","family":"Farabbi","sequence":"additional","affiliation":[{"name":"Information and Bioengineering"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-9699-6274","authenticated-orcid":true,"given":"Francesco","family":"Latino","sequence":"additional","affiliation":[{"name":"Information and Bioengineering"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2519-0720","authenticated-orcid":true,"given":"Matteo","family":"Rossi","sequence":"additional","affiliation":[{"name":"EssilorLuxottica"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0803-5385","authenticated-orcid":false,"given":"Niccol\u00f3","family":"Antonello","sequence":"additional","affiliation":[{"name":"EssilorLuxottica"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3995-8673","authenticated-orcid":false,"given":"Pietro","family":"Cerveri","sequence":"additional","affiliation":[{"name":"Universit\u00e1 di Pavia"},{"name":"Information and Bioengineering"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6276-6314","authenticated-orcid":false,"given":"Luca","family":"Mainardi","sequence":"additional","affiliation":[{"name":"Information and Bioengineering"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"266","published-online":{"date-parts":[[2026,9,29]]},"reference":[{"key":"pmeaae99abbib1","doi-asserted-by":"publisher","DOI":"10.1088\/1741-2552\/ade566","type":"journal-article","article-title":"Artifact-reference multivariate backward regression (ARMBR): a novel method for EEG blink artifact removal with minimal data requirements","volume":"22","author":"Alkhoury","year":"2025","journal-title":"J. Neural Eng."},{"key":"pmeaae99abbib2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2024.128354","type":"journal-article","article-title":"Toward cross-subject and cross-session generalization in EEG-based emotion recognition: systematic review, taxonomy and methods","volume":"604","author":"Apicella","year":"2024","journal-title":"Neurocomputing"},{"key":"pmeaae99abbib3","doi-asserted-by":"publisher","first-page":"5770","DOI":"10.3390\/s25185770","type":"journal-article","article-title":"A systematic review of techniques for artifact detection and artifact category identification in electroencephalography from wearable devices","volume":"25","author":"Arpaia","year":"2025","journal-title":"Sensors"},{"key":"pmeaae99abbib4","first-page":"pp 195","type":"conference-proceedings","article-title":"Artifacts removal from low-density EEG measured with dry electrodes","author":"Arpaia","year":"2024"},{"key":"pmeaae99abbib5","doi-asserted-by":"publisher","first-page":"23621","DOI":"10.1109\/JSEN.2023.3307444","type":"journal-article","article-title":"Low-density EEG correction with multivariate decomposition and subspace reconstruction","volume":"23","author":"Arpaia","year":"2023","journal-title":"IEEE Sens. J."},{"key":"pmeaae99abbib6","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2024.1373515","type":"journal-article","article-title":"Data leakage in deep learning studies of translational EEG","volume":"18","author":"Brookshire","year":"2024","journal-title":"Front. Neurosci."},{"key":"pmeaae99abbib7","doi-asserted-by":"publisher","first-page":"21257","DOI":"10.1109\/JSEN.2022.3208768","type":"journal-article","article-title":"A method for optimizing the artifact subspace reconstruction performance in low-density EEG","volume":"22","author":"Cataldo","year":"2022","journal-title":"IEEE Sens. J."},{"key":"pmeaae99abbib8","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2022.119586","type":"journal-article","article-title":"IC-U-Net: a U-Net-based denoising autoencoder using mixtures of independent components for automatic EEG artifact removal","volume":"263","author":"Chuang","year":"2022","journal-title":"NeuroImage"},{"key":"pmeaae99abbib9","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1016\/S0987-7053(00)00055-1","type":"journal-article","article-title":"Removal of ocular artifact from the EEG: a review","volume":"30","author":"Croft","year":"2000","journal-title":"Neurophysiol. Clin.\/Clin. Neurophysiol."},{"key":"pmeaae99abbib10","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1016\/j.jneumeth.2003.10.009","type":"journal-article","article-title":"EEGLAB: an open source toolbox for analysis of single-trial EEG dynamics including independent component analysis","volume":"134","author":"Delorme","year":"2004","journal-title":"J. Neurosci. Methods"},{"key":"pmeaae99abbib11","doi-asserted-by":"publisher","first-page":"98450","DOI":"10.1109\/ACCESS.2022.3206782","type":"journal-article","article-title":"Embedded machine learning using microcontrollers in wearable and ambulatory systems for health and care applications: a review","volume":"10","author":"Diab","year":"2022","journal-title":"IEEE Access"},{"key":"pmeaae99abbib12","first-page":"pp 1","type":"conference-proceedings","article-title":"A two-stage deep learning approach for EEG artifact removal and classification: towards reliable wearable applications","author":"Farabbi","year":"2025"},{"key":"pmeaae99abbib13","doi-asserted-by":"publisher","first-page":"601","DOI":"10.3390\/s19030601","type":"journal-article","article-title":"Quality assessment of single-channel EEG for wearable devices","volume":"19","author":"Grosselin","year":"2019","journal-title":"Sensors"},{"key":"pmeaae99abbib14","first-page":"pp 1026","type":"conference-proceedings","article-title":"Delving deep into rectifiers: surpassing human-level performance on imageNet classification","author":"He","year":"2015"},{"key":"pmeaae99abbib15","doi-asserted-by":"publisher","DOI":"10.1088\/1741-2552\/acbc4b","type":"journal-article","article-title":"A multi-task and multi-channel convolutional neural network for semi-supervised neonatal artefact detection","volume":"20","author":"Hermans","year":"2023","journal-title":"J. Neural Eng."},{"key":"pmeaae99abbib16","doi-asserted-by":"publisher","first-page":"2980","DOI":"10.1038\/s41598-024-52551-0","type":"journal-article","article-title":"Minimizing artifact-induced false-alarms for seizure detection in wearable EEG devices with gradient-boosted tree classifiers","volume":"14","author":"Ingolfsson","year":"2024","journal-title":"Sci. Rep."},{"key":"pmeaae99abbib17","doi-asserted-by":"publisher","first-page":"287","DOI":"10.1016\/j.neucli.2016.07.002","type":"journal-article","article-title":"Methods for artifact detection and removal from scalp EEG: a review","volume":"46","author":"Islam","year":"2016","journal-title":"Neurophysiol. Clin.\/Clin. Neurophysiol."},{"key":"pmeaae99abbib18","doi-asserted-by":"publisher","DOI":"10.1088\/1741-2552\/aadea0","type":"journal-article","article-title":"MOABB: trustworthy algorithm benchmarking for BCIs","volume":"15","author":"Jayaram","year":"2018","journal-title":"J. Neural Eng."},{"key":"pmeaae99abbib19","first-page":"pp 221","type":"book","article-title":"Artifact detection in neonatal EEG using Gaussian mixture models","author":"Kauppila","year":"2018"},{"key":"pmeaae99abbib20","article-title":"Eeg eye artifact dataset","author":"Kobler","year":"2021","type":"other"},{"key":"pmeaae99abbib21","first-page":"pp 1","type":"conference-proceedings","article-title":"AttentivU: a wearable pair of EEG and EOG glasses for real-time physiological processing","author":"Kosmyna","year":"2019"},{"key":"pmeaae99abbib22","doi-asserted-by":"publisher","first-page":"IMAG.a.136","DOI":"10.1162\/IMAG.a.136","type":"journal-article","article-title":"The lab streaming layer for synchronized multimodal recording","volume":"3","author":"Kothe","year":"2025","journal-title":"Imaging Neurosci."},{"key":"pmeaae99abbib23","doi-asserted-by":"publisher","first-page":"1193","DOI":"10.3390\/electronics14061193","type":"journal-article","article-title":"An optimized hybrid approach to denoising of EEG signals using CNN and LMS filtering","volume":"14","author":"Nair","year":"2025","journal-title":"Electronics"},{"key":"pmeaae99abbib24","doi-asserted-by":"publisher","DOI":"10.1088\/1741-2552\/ae4271","type":"journal-article","article-title":"Form factor meets function: anatomy-dependent electrode-skin coupling and signal content in consumer eyewear EEG systems","volume":"23","author":"Palmisciano","year":"2026","journal-title":"J. Neural Eng."},{"key":"pmeaae99abbib25","doi-asserted-by":"crossref","DOI":"10.1109\/EMBC48229.2022.9871916","type":"other","article-title":"Transformer convolutional neural networks for automated artifact detection in scalp EEG","author":"Peh","year":"2022"},{"key":"pmeaae99abbib26","doi-asserted-by":"publisher","first-page":"181","DOI":"10.1016\/j.neuroimage.2019.05.026","type":"journal-article","article-title":"ICLabel: an automated electroencephalographic independent component classifier, dataset and website","volume":"198","author":"Pion-Tonachini","year":"2019","journal-title":"NeuroImage"},{"key":"pmeaae99abbib27","doi-asserted-by":"publisher","first-page":"278","DOI":"10.3389\/fnhum.2012.00278","type":"journal-article","article-title":"Combining EEG and eye tracking: identification, characterization and correction of eye movement artifacts in electroencephalographic data","volume":"6","author":"Pl\u00f6chl","year":"2012","journal-title":"Front. Hum. Neurosci."},{"key":"pmeaae99abbib28","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/LSENS.2025.3563390","type":"journal-article","article-title":"EEG artifact removal at the edge using ai hardware","volume":"9","author":"Saleh","year":"2025","journal-title":"IEEE Sens. Lett."},{"key":"pmeaae99abbib29","doi-asserted-by":"publisher","first-page":"45","DOI":"10.1109\/MDAT.2024.3483034","type":"journal-article","article-title":"BiomedBench: a benchmark suite of TinyML biomedical applications for low-power wearables","volume":"42","author":"Samakovlis","year":"2025","journal-title":"IEEE Des. Test"},{"key":"pmeaae99abbib30","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2015","type":"conference-proceedings"},{"key":"pmeaae99abbib31","doi-asserted-by":"publisher","first-page":"108","DOI":"10.1016\/j.neucom.2020.04.029","type":"journal-article","article-title":"A novel end-to-end 1D-ResCNN model to remove artifact from EEG signals","volume":"404","author":"Sun","year":"2020","journal-title":"Neurocomputing"},{"key":"pmeaae99abbib32","first-page":"1","type":"journal-article","article-title":"Fundamentals of EEG measurement","volume":"2","author":"Teplan","year":"2002","journal-title":"Meas. Sci. Rev."},{"key":"pmeaae99abbib33","doi-asserted-by":"publisher","first-page":"135","DOI":"10.1007\/BF02534144","type":"journal-article","article-title":"Signal-space projection method for separating MEG or EEG into components","volume":"35","author":"Uusitalo","year":"1997","journal-title":"Med. Biol. Eng. Comput."},{"key":"pmeaae99abbib34","doi-asserted-by":"publisher","first-page":"1313","DOI":"10.1016\/j.neunet.2009.07.020","type":"journal-article","article-title":"Time domain parameters as a feature for eeg-based brain\u2013computer interfaces","volume":"22","author":"Vidaurre","year":"2009","journal-title":"Neural Netw."},{"key":"pmeaae99abbib35","doi-asserted-by":"publisher","first-page":"3111","DOI":"10.1109\/TBME.2024.3408331","type":"journal-article","article-title":"Deep autoencoder for real-time single-channel EEG cleaning and its smartphone implementation using tensorflow lite with hardware\/software acceleration","volume":"71","author":"Xing","year":"2024","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"pmeaae99abbib36","doi-asserted-by":"publisher","DOI":"10.1088\/1741-2552\/ac63eb","type":"journal-article","article-title":"Embedding decomposition for artifacts removal in EEG signals","volume":"19","author":"Yu","year":"2022","journal-title":"J. Neural Eng."},{"key":"pmeaae99abbib37","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-025-29893-4","type":"journal-article","article-title":"EEG glasses for real-time brain electrical activity monitoring","volume":"15","author":"Zanetti","year":"2025","journal-title":"Sci. Rep."},{"key":"pmeaae99abbib38","doi-asserted-by":"publisher","first-page":"265","DOI":"10.1109\/TBME.2021.3092206","type":"journal-article","article-title":"Real-time EEG-based cognitive workload monitoring on wearable devices","volume":"69","author":"Zanetti","year":"2022","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"pmeaae99abbib39","first-page":"pp 1265","type":"conference-proceedings","article-title":"A novel convolutional neural network model to remove muscle artifacts from EEG","author":"Zhang","year":"2021"},{"key":"pmeaae99abbib40","doi-asserted-by":"publisher","DOI":"10.1088\/1741-2552\/ac2bf8","type":"journal-article","article-title":"EEGdenoiseNet: a benchmark dataset for deep learning solutions of EEG denoising","volume":"18","author":"Zhang","year":"2021","journal-title":"J. Neural Eng."}],"container-title":["Physiological Measurement"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6579\/ae99ab","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6579\/ae99ab\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6579\/ae99ab","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6579\/ae99ab\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6579\/ae99ab\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6579\/ae99ab\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6579\/ae99ab\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6579\/ae99ab\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T07:20:08Z","timestamp":1790666408000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6579\/ae99ab"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,29]]},"references-count":40,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2026,9,29]]},"published-print":{"date-parts":[[2026,9,30]]}},"URL":"https:\/\/doi.org\/10.1088\/1361-6579\/ae99ab","relation":{},"ISSN":["0967-3334","1361-6579"],"issn-type":[{"value":"0967-3334","type":"print"},{"value":"1361-6579","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,29]]},"assertion":[{"value":"A gated artifact management pipeline for low-density eyewear EEG","name":"article_title","label":"Article Title"},{"value":"Physiological Measurement","name":"journal_title","label":"Journal Title"},{"value":"paper","name":"article_type","label":"Article Type"},{"value":"\u00a9 2026 The Author(s). Published on behalf of Institute of Physics and Engineering in Medicine by IOP Publishing Ltd","name":"copyright_information","label":"Copyright Information"},{"value":"2026-05-17","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2026-08-13","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2026-09-29","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}